DPED: Bio-inspired dual-pathway network for edge detection

Abstract

Edge detection is significant as the basis of high-level visual tasks. Most encoder-decoder edge detection methods used convolutional neural networks, such as VGG16 or Resnet, as the encoding network. Studies on designing decoding networks have achieved good results. Swin Transformer (Swin) has recently attracted much attention in various visual tasks as a possible alternative to convolutional neural networks. Physiological studies have shown that there are two visual pathways that converge in the visual cortex in the biological vision system, and that complex information transmission and communication is widespread. Inspired by the research on Swin and the biological vision pathway, we have designed a two-pathway encoding network. The first pathway network is the fine-tuned Swin; the second pathway network mainly comprises deep separable convolution. To simulate attention transmission and feature fusion between the first and second pathway networks, we have designed a second-pathway attention module and a pathways fusion module. Our proposed method outperforms the CNN-based SOTA method BDCN on BSDS500 datasets. Moreover, our proposed method and the Transformer-based SOTA method EDTER have their own performance advantages. In terms of FLOPs and FPS, our method has more benefits than EDTER.

Bio-Inspired Network for Diagnosing Liver Steatosis in Ultrasound Images

“…The Swin Transformer [27] achieved the best performance in multiple computer vision tasks, breaking the dominance of CNN in computer vision tasks. Later, some researchers were inspired to combine biological vision with transformers, and proposed an edge detection model that simulates visual pathways [28] and an edge detection network that simulates the selective mechanism of the visual cortex [29], which have achieved good performance. This also provides a good theoretical basis and direction for our research.…”